Implementation Aspects of Graph Neural Networks
Aleksy Barcz , Zbigniew Szymański , Stanisław Jankowski
AbstractThis article summarises the results of implementation of a Graph Neural Network classifier. The Graph Neural Network model is a connectionist model, capable of processing various types of structured data, including non- positional and cyclic graphs. In order to operate correctly, the GNN model must implement a transition function being a contraction map, which is assured by imposing a penalty on model weights. This article presents research results concerning the impact of the penalty parameter on the model training process and the practical decisions that were made during the GNN implementation process.
|Book||Romaniuk Ryszard (eds.): Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013, vol. 8903, 2013, SPIE P.O. Box 10, Bellingham, Washington 98227-0010 USA , SPIE, ISBN 9780819497857, [ISSN 0277-786X ], 410 p., DOI:10.1117/12.2049644|
|Keywords in English||Graph Neural Network, GNN, graph, classification, contraction map|
|Project||Development of new methods and algorithms in the following areas: computer graphics, artificial intelligence, and information systems, and distributed systems . Project leader: Rybiński Henryk,
, Phone: +48 22 234 7731, start date 29-05-2013, planned end date 31-12-2013, end date 30-11-2014, II/2013/DS/1, Completed
|Score|| = 10.0, 29-08-2020, BookChapterMatConfByIndicator|
= 15.0, 29-08-2020, BookChapterMatConfByIndicator
|Publication indicators||= 0; = 0|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.